检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Lan, Chao Chandrasekaran, Sai Nivedita Huan, Jun Department of Electrical Engineering and Computer Science University of Kansas LawrenceKS66045 United States Bioengineering Department University of Kansas LawrenceKS66045 United States

—In cheminformatics, compound-target binding profiles has been a main source of data for research. For data repositories that only provide positive profiles, a popular assumption is that unreported profiles are all negative. In this paper, we caution audience not to take this assumption for granted, and present empirical evidence of its ineffectiveness from a machine learning perspective. Our examination is based on a setting where binding profiles are used as features to train predictive models;we show (1) prediction performance degrades when the assumption fails and (2) explicit recovery of unreported profiles improves prediction performance. In particular, we propose a framework that jointly recovers profiles and learns predictive model, and show it achieves further performance improvement. The presented study not only suggests applying matrix recovery methods to recover unreported profiles, but also initiates a new missing feature problem which we called Learning with Positive and Unknown Features. Copyright © 2017, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Nanophotonic engineering of far-field thermal emitters

arXiv

引用

arXiv 2018年

作者： Baranov, Denis G. Xiao, Yuzhe Nechepurenko, Igor A. Krasnok, Alex Alù, Andrea Kats, Mikhail A. Department of Physics Chalmers University of Technology Gothenburg412 96 Sweden Department of Electrical and Computer Engineering University of Wisconsin-Madison WI United States Dukhov Research Institute of Automatics 22 Sushchevskaya Moscow127055 Russia Photonics Initiative Advanced Science Research Center City University of New York NY10031 United States Physics Program Graduate Center City University of New York NY10016 United States Department of Electrical Engineering City College of The City University of New York New York10031 United States Department of Materials Science and Engineering University of Wisconsin-Madison WI United States Department of Physics University of Wisconsin-Madison WI United States

Thermal emission is a ubiquitous and fundamental process by which all objects at non-zero temperatures radiate electromagnetic energy. This process is often presented to be incoherent in both space and time, resulting in broadband, omnidirectional light emission toward the far field, with a spectral density related to the emitter temperature by Planck’s law. Over the past two decades, there has been considerable progress in engineering the spectrum, directionality, polarization, and temporal response of thermally emitted light using nanostructured materials. This review summarizes the basic physics of thermal emission, lays out various nanophotonic approaches to engineer thermal-emission in the far field, and highlights several relevant applications, including energy harvesting, lighting, and radiative cooling. Copyright © 2018, The Authors. All rights reserved.

关键词： Spectral density

来源：评论

学校读者我要写书评

暂无评论

On structural controllability of symmetric (Brain) networks

arXiv

引用

arXiv 2017年

作者： Menara, Tommaso Gu, Shi Bassett, Danielle S. Pasqualetti, Fabio Mechanical Engineering Department University of California Riverside United States Department of Computer Science and Engineering University of Electronic Science and Technology Chengdu China Department of Bioengineering Department of Electrical and Systems Engineering Department of Physics and Astronomy Department of Neurology University of Pennsylvania United States

The question of controllability of natural and man-made network systems has recently received considerable attention. In the context of the human brain, the study of controllability may not only shed light into the organization and function of different neural circuits, but also inform the design and implementation of minimally invasive yet effective intervention protocols to treat neurological disorders. While the characterization of brain controllability is still in its infancy, some results have recently appeared and given rise to scientific debate. Among these, [1] has numerically shown that a class of brain networks constructed from DSI/DTI imaging data are controllable from one brain region. That is, a single brain region is theoretically capable of moving the whole brain network towards any desired target state. In this note we provide evidence supporting controllability of brain networks from a single region as discussed in [1], thus contradicting the main conclusion and methods developed in [2]. Copyright © 2017, The Authors. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Constructing synthetic biology workflows in the cloud

引用

engineering Biology 2017年第1期1卷 61-65页

作者： Mısırlı, Göksel Madsen, Curtis De Murieta, Iñaki Sainz Bultelle, Matthieu Flanagan, Keith Pocock, Matthew Hallinan, Jennifer McLaughlin, James Alastair Clark-Casey, Justin Lyne, Mike Micklem, Gos Stan, Guy-Bart Kitney, Richard Wipat, Anil School of Computing Science Newcastle University Newcastle upon Tyne United Kingdom Electrical and Computer Engineering Department Boston University Boston United States Department of Bioengineering Imperial College London London United Kingdom Turing Ate My Hamster Ltd Tyne and Wear United Kingdom School of Biological Sciences Macquarie University Sydney Australia Department of Genetics Cambridge Systems Biology Centre University of Cambridge Cambridge United Kingdom

The synthetic biology design process has traditionally been heavily dependent upon manual searching, acquisition and integration of existing biological data. A large amount of such data is already available from Internet-based resources, but data exchange between these resources is often undertaken manually. Automating the communication between different resources can be done by the generation of computational workflows to achieve complex tasks that cannot be carried out easily or efficiently by a single resource. Computational workflows involve the passage of data from one resource, or process, to another in a distributed computing environment. In a typical bioinformatics workflow, the predefined order in which processes are invoked in a synchronous fashion and are described in a workflow definition document. However, in synthetic biology the diversity of resources and manufacturing tasks required favour a more flexible model for process execution. Here, the authors present the Protocol for Linking External Nodes (POLEN), a Cloud-based system that facilitates synthetic biology design workflows that operate asynchronously. Messages are used to notify POLEN resources of events in real time, and to log historical events such as the availability of new data, enabling networks of cooperation. POLEN can be used to coordinate the integration of different synthetic biology resources, to ensure consistency of information across distributed repositories through added support for data standards, and ultimately to facilitate the synthetic biology life cycle for designing and implementing biological systems. © 2017 Eng. Biol. All rights reserved.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Network Topology Mapping from Partial Virtual Coordinates and Graph Geodesics

arXiv

引用

arXiv 2017年

作者： Jayasumana, Anura P. Paffenroth, Randy Ramasamy, Sridhar Department of Electrical & Computer Engineering Colorado State University Fort CollinsCO80525 Department of Mathematical Sciences Department of Computer Science Data Science Program Worcester Polytechnic Institute WorcesterMA01609

For many important network types (e.g., sensor networks in complex harsh environments and social networks) physical coordinate systems (e.g., Cartesian), and physical distances (e.g., Euclidean), are either difficult to discern or inappropriate. Accordingly, Topology Preserving Maps (TPMs) derived from a Virtual-Coordinate (VC) system representing the distance to a small set of anchors is an attractive alternative to physical coordinates for many network algorithms. Herein, we present an approach, based on the theory of low-rank matrix completion, to recover geometric properties of a network with only partial information about the VCs of nodes. In particular, our approach is a combination of geodesic recovery concepts and low-rank matrix completion, generalized to the case of hop-distances in graphs. Distortion evaluated using the change of distance among node pairs shows that even with up to 40% to 60% of random coordinates missing, accurate TPMs can be obtained. TPM generation can now also be based on different context appropriate VC systems or measurements as long as they characterize each node with distances to a small set of random nodes (instead of a global set of anchors). The proposed method is a significant generalization that allows the topology to be extracted from a random set of graph geodesics, making it applicable in contexts such as social networks where VC generation may not be *** Codes 15A83 Copyright © 2017, The Authors. All rights reserved.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

High-depth African genomes inform human migration and health (vol 586, pg 741, 2020)

引用

NATURE 2021年第7856期592卷 E26-E26页

作者： Choudhury, Ananyo Aron, Shaun Botigue, Laura R. Sengupta, Dhriti Botha, Gerrit Bensellak, Taoufik Wells, Gordon Kumuthini, Judit Shriner, Daniel Fakim, Yasmina J. Ghoorah, Anisah W. Dareng, Eileen Odia, Trust Falola, Oluwadamilare Adebiyi, Ezekiel Hazelhurst, Scott Mazandu, Gaston Nyangiri, Oscar A. Mbiyavanga, Mamana Benkahla, Alia Kassim, Samar K. Mulder, Nicola Adebamowo, Sally N. Chimusa, Emile R. Muzny, Donna Metcalf, Ginger Gibbs, Richard A. Matovu, Enock Bucheton, Bruno Hertz-Fowler, Christiane Koffi, Mathurin Macleod, Annette Mumba-Ngoyi, Dieudonne Noyes, Harry Nyangiri, Oscar A. Simo, Gustave Simuunza, Martin Rotimi, Charles Ramsay, Michele Choudhury, Ananyo Choudhury, Ananyo Aron, Shaun Botigue, Laura Sengupta, Dhriti Botha, Gerrit Bensellak, Taoufik Wells, Gordon Kumuthini, Judit Shriner, Daniel Fakim, Yasmina J. Ghoorah, Anisah W. Dareng, Eileen Odia, Trust Falola, Oluwadamilare Adebiyi, Ezekiel Hazelhurst, Scott Mazandu, Gaston Nyangiri, Oscar A. Mbiyavanga, Mamana Benkahla, Alia Kassim, Samar K. Mulder, Nicola Adebamowo, Sally N. Chimusa, Emile R. Rotimi, Charles Ramsay, Michele Adeyemo, Adebowale A. Lombard, Zane Hanchard, Neil A. Adebamowo, Clement Agongo, Godfred Boua, Romuald P. Oduro, Abraham Sorgho, Hermann Landoure, Guida Cisse, Lassana Diarra, Salimata Samassekou, Oumar Anabwani, Gabriel Matshaba, Mogomotsi Joloba, Moses Kekitiinwa, Adeodata Mardon, Graeme Mpoloka, Sununguko W. Kyobe, Samuel Mlotshwa, Busisiwe Mwesigwa, Savannah Retshabile, Gaone Williams, Lesedi Wonkam, Ambroise Moussa, Ahmed Adu, Dwomoa Ojo, Akinlolu Burke, David Salako, Babatunde O. Matovu, Enock Bucheton, Bruno Hertz-Fowler, Christiane Koffi, Mathurin Macleod, Annette Mumba-Ngoyi, Dieudonne Noyes, Harry Nyangiri, Oscar A. Simo, Gustave Simuunza, Martin Awadalla, Philip Bruat, Vanessa Gbeha, Elias Adeyemo, Adebowale A. Lombard, Zane Hanchard, Neil A. Sydney Brenner Institute for Molecular Bioscience Faculty of Health Sciences University of the Witwatersrand Johannesburg South Africa School of Electrical and Information Engineering University of the Witwatersrand Johannesburg South Africa Division of Human Genetics National Health Laboratory Service and School of Pathology Faculty of Health Sciences University of the Witwatersrand Johannesburg South Africa Navrongo Health Research Centre Navrongo Ghana Clinical Research Unit of Nanoro Institut de Recherche en Sciences de la Sante Bobo-Dioulasso Burkina Faso Center for Research in Agricultural Genomics (CRAG) Plant and Animal Genomics Program CSIC-IRTA-UAB-UB Barcelona Spain Computational Biology Division and H3ABioNet Department of Integrative Biomedical Sciences IDM University of Cape Town Cape Town South Africa System and Data Engineering Team Abdelmalek Essaadi University ENSA Tangier Morocco Centre for Proteomic and Genomic Research (CPGR) Cape Town South Africa South African National Bioinformatics Institute University of the Western Cape Bellville South Africa Africa Health Research Institute Durban South Africa Center for Research on Genomics and Global Health National Human Genome Research Institute National Institutes of Health Bethesda MD USA Department of Agriculture and Food Science Faculty of Agriculture University of Mauritius Reduit Mauritius Department of Digital Technologies Faculty of Information Communication & Digital Technologies University of Mauritius Reduit Mauritius Department of Public Health and Primary Care University of Cambridge Cambridge UK Institute of Human Virology Nigeria Abuja Nigeria Department of Epidemiology and Public Health University of Maryland School of Medicine University of Maryland Baltimore Baltimore MD USA University of Maryland Greenebaum Comprehensive Cancer Center University of Maryland School of Medicine University of Maryland Baltimore Baltimore MD USA Institute of Human Virology and Greeneba

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Enhancing untargeted metabolomics using metadata-based source annotation

引用

Nature biotechnology 2023年第11期41卷 1656页

作者： Julia M Gauglitz Kiana A West Wout Bittremieux Candace L Williams Kelly C Weldon Morgan Panitchpakdi Francesca Di Ottavio Christine M Aceves Elizabeth Brown Nicole C Sikora Alan K Jarmusch Cameron Martino Anupriya Tripathi Michael J Meehan Kathleen Dorrestein Justin P Shaffer Roxana Coras Fernando Vargas Lindsay DeRight Goldasich Tara Schwartz MacKenzie Bryant Gregory Humphrey Abigail J Johnson Katharina Spengler Pedro Belda-Ferre Edgar Diaz Daniel McDonald Qiyun Zhu Emmanuel O Elijah Mingxun Wang Clarisse Marotz Kate E Sprecher Daniela Vargas-Robles Dana Withrow Gail Ackermann Lourdes Herrera Barry J Bradford Lucas Maciel Mauriz Marques Juliano Geraldo Amaral Rodrigo Moreira Silva Flavio Protasio Veras Thiago Mattar Cunha Rene Donizeti Ribeiro Oliveira Paulo Louzada-Junior Robert H Mills Paulina K Piotrowski Stephanie L Servetas Sandra M Da Silva Christina M Jones Nancy J Lin Katrice A Lippa Scott A Jackson Rima Kaddurah Daouk Douglas Galasko Parambir S Dulai Tatyana I Kalashnikova Curt Wittenberg Robert Terkeltaub Megan M Doty Jae H Kim Kyung E Rhee Julia Beauchamp-Walters Kenneth P Wright Maria Gloria Dominguez-Bello Mark Manary Michelli F Oliveira Brigid S Boland Norberto Peporine Lopes Monica Guma Austin D Swafford Rachel J Dutton Rob Knight Pieter C Dorrestein Collaborative Mass Spectrometry Innovation Center University of California San Diego La Jolla CA USA. Skaggs School of Pharmacy and Pharmaceutical Sciences University of California San Diego La Jolla CA USA. Beckman Center for Conservation Research San Diego Zoo Wildlife Alliance Escondido CA USA. Center for Microbiome Innovation Joan and Irwin Jacobs School of Engineering University of California San Diego La Jolla CA USA. Division of Biological Sciences University of California San Diego La Jolla CA USA. Department of Pediatrics School of Medicine University of California San Diego La Jolla CA USA. Bioinformatics and Systems Biology Program University of California San Diego La Jolla CA USA. Division of Rheumatology Allergy & Immunology Department of Medicine University of California San Diego La Jolla CA USA. Division of Epidemiology and Community Health School of Public Health University of Minnesota Minneapolis MN USA. Department of Integrative Physiology University of Colorado Boulder Boulder CO USA. Department of Population Health Sciences University of Wisconsin-Madison Madison WI USA. Servicio Autónomo Centro Amazónico de Investigación y Control de Enfermedades Tropicales Simón Bolívar Puerto Ayacucho Amazonas Venezuela. Department of Pediatrics Billings Clinic Billings MT USA. Department of Animal Science Michigan State University East Lansing MI USA. Department of Pharmacology Ribeirão Preto Medicinal School Center of Research in Inflammatory Diseases University of São Paulo Ribeirão Preto Sao Paolo Brazil. Multidisciplinary Health Institute Federal University of Bahia Vitória da Conquista Bahia Brazil. NPPNS Department of Biomolecular Sciences School of Pharmaceutical Sciences of Ribeirão Preto University of São Paulo Ribeirão Preto Sao Paolo Brazil. Department of Internal Medicine Ribeirão Preto Medical School Center of Research in Inflammatory Diseases University of São Paulo Ribeirão Preto Sao Paolo Brazil. Department

来源：评论

学校读者我要写书评

暂无评论

Learning-based spatiotemporal regularization and integration of tracking methods for regional 4D cardiac deformation analysis 1

引用

20th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2017

作者： Lu, Allen Zontak, Maria Parajuli, Nripesh Stendahl, John C. Boutagy, Nabil Eberle, Melissa Alkhalil, Imran O’Donnell, Matthew Sinusas, Albert J. Duncan, James S. Department of Biomedical Engineering Yale University New HavenCT United States Department of Electrical Engineering Yale University New HavenCT United States Department of Internal Medicine Yale University New HavenCT United States Department of Radiology and Biomedical Imaging Yale University New HavenCT United States Department of Bioengineering University of Washington SeattleWA United States College of Computer and Information Science Northeastern University SeattleWA United States

ISBN: (数字)9783319661858

ISBN: (纸本)9783319661841

Dense cardiac motion tracking and deformation analysis from echocardiography is important for detection and localization of myocardial dysfunction. However, tracking methods are often unreliable due to inherent ultrasound imaging properties. In this work, we propose a new data-driven spatiotemporal regularization strategy. We generate 4D Lagrangian displacement patches from different input sources as training data and learn the regularization procedure via a multi-layered perceptron (MLP) network. The learned regularization procedure is applied to initial noisy tracking results. We further propose a framework for integrating tracking methods to produce better overall estimations. We demonstrate the utility of this approach on block-matching, surface tracking, and free-form deformation-based methods. Finally, we quantitatively and qualitatively evaluate our performance on both tracking and strain accuracy using both synthetic and in vivo data. © Springer International Publishing AG 2017.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

Estimates, trends, and drivers of the global burden of type 2 diabetes attributable to PM_2·5 air pollution, 1990–2019: an analysis of data from the Global Burden of Disease Study 2019

引用

The Lancet Planetary Health 2022年第7期6卷 e586-e600页

作者： Burkart, Katrin Causey, Kate Cohen, Aaron J Wozniak, Sarah S Salvi, Devashri Digvijay Abbafati, Cristiana Adekanmbi, Victor Adsuar, Jose C Ahmadi, Keivan Alahdab, Fares Al-Aly, Ziyad Alipour, Vahid Alvis-Guzman, Nelson Amegah, Adeladza Kofi Andrei, Catalina Liliana Andrei, Tudorel Ansari, Fereshteh Arabloo, Jalal Aremu, Olatunde Aripov, Timur Babaee, Ebrahim Banach, MacIej Barnett, Anthony Bärnighausen, Till Winfried Bedi, Neeraj Behzadifar, Masoud Béjot, Yannick Bennett, Derrick A Bensenor, Isabela M Bernstein, Robert S Bhattacharyya, Krittika Bijani, Ali Biondi, Antonio Bohlouli, Somayeh Breitner, Susanne Brenner, Hermann Butt, Zahid A Cámera, Luis Alberto Cantu-Brito, Carlos Carvalho, Felix Cerin, Ester Chattu, Vijay Kumar Chauhan, Bal Govind Choi, Jee-Young Jasmine Chu, Dinh-Toi Dai, Xiaochen Dandona, Lalit Dandona, Rakhi Daryani, Ahmad Davletov, Kairat De Courten, Barbora Demeke, Feleke Mekonnen Denova-Gutiérrez, Edgar Dharmaratne, Samath Dhamminda Dhimal, Meghnath Diaz, Daniel Djalalinia, Shirin Duncan, Bruce B El Sayed Zaki, Maysaa Eskandarieh, Sharareh Fareed, Mohammad Farzadfar, Farshad Fattahi, Nazir Fazlzadeh, Mehdi Fernandes, Eduarda Filip, Irina Fischer, Florian Foigt, Nataliya A Freitas, Marisa Ghashghaee, Ahmad Gill, Paramjit Singh Ginawi, Ibrahim Abdelmageed Gopalani, Sameer Vali Guo, Yuming Gupta, Rajat Das Habtewold, Tesfa Dejenie Hamadeh, Randah R Hamidi, Samer Hankey, Graeme J Hasanpoor, Edris Hassen, Hamid Yimam Hay, Simon I Heibati, Behzad Hole, Michael K Hossain, Naznin Househ, Mowafa Irvani, Seyed Sina Naghibi Jaafari, Jalil Jakovljevic, Mihajlo Jha, Ravi Prakash Jonas, Jost B Jozwiak, Jacek Jerzy Kasaeian, Amir Kaydi, Neda Khader, Yousef Saleh Khafaie, Morteza Abdullatif Khan, Ejaz Ahmad Khan, Junaid Khan, Md Nuruzzaman Khatab, Khaled Khater, Amir M Kim, Yun Jin Kimokoti, Ruth W Kisa, Adnan Kivimäki, Mika Knibbs, Luke D Kosen, Soewarta Koul, Parvaiz A Koyanagi, Ai Defo, Barthelemy Kuate Kugbey, Nuworza Lauriola, Paolo Lee, Paul H Leili, Mostafa Lewycka, Sonia Li, Shanshan Lim, Lee-Ling Li Institute for Health Metrics and Evaluation University of Washington Seattle WA United States Department of Health Metrics Sciences School of Medicine University of Washington Seattle WA United States Division of Plastic and Reconstructive Surgery University of Washington Seattle WA United States Research Insights and Innovation Seattle WA United States Health Effects Institute Boston MA United States School of Public Health Boston University Boston MA United States Department of Juridical and Economic Studies La Sapienza University Rome Italy Department of Population Medicine Cardiff University Cardiff United Kingdom Sport Science Department University of Extremadura Badajoz Spain School of Public Health Imperial College London London United Kingdom Department of Primary Care and Public Health Imperial College London London United Kingdom Mayo Evidence-based Practice Center Mayo Clinic Foundation for Medical Education and Research Rochester MN United States John T. Milliken Department of Internal Medicine Washington University in St. Louis St. Louis MO United States Clinical Epidemiology Center US Department of Veterans Affairs (VA) St Louis MO United States Health Management and Economics Research Center Iran University of Medical Sciences Tehran Iran Department of Health Economics Iran University of Medical Sciences Tehran Iran Preventive Medicine and Public Health Research Center Iran University of Medical Sciences Tehran Iran Pars Advanced and Minimally Invasive Medical Manners Research Center Iran University of Medical Sciences Tehran Iran Department of Community and Family Medicine Iran University of Medical Sciences Tehran Iran Research Group in Hospital Management and Health Policies Universidad de la Costa (University of the Coast) Barranquilla Colombia Research Group in Health Economics University of Cartagena Cartagena Colombia Department of Biomedical Science University of Cape Coast Cape Coast Ghana Cardiology Department Ca

Background: Experimental and epidemiological studies indicate an association between exposure to particulate matter (PM) air pollution and increased risk of type 2 diabetes. In view of the high and increasing prevalence of diabetes, we aimed to quantify the burden of type 2 diabetes attributable to PM_2·5 originating from ambient and household air pollution. Methods: We systematically compiled all relevant cohort and case-control studies assessing the effect of exposure to household and ambient fine particulate matter (PM_2·5) air pollution on type 2 diabetes incidence and mortality. We derived an exposure–response curve from the extracted relative risk estimates using the MR-BRT (meta-regression—Bayesian, regularised, trimmed) tool. The estimated curve was linked to ambient and household PM_2·5 exposures from the Global Burden of Diseases, Injuries, and Risk Factors Study 2019, and estimates of the attributable burden (population attributable fractions and rates per 100 000 population of deaths and disability-adjusted life-years) for 204 countries from 1990 to 2019 were calculated. We also assessed the role of changes in exposure, population size, age, and type 2 diabetes incidence in the observed trend in PM_2·5-attributable type 2 diabetes burden. All estimates are presented with 95% uncertainty intervals. Findings: In 2019, approximately a fifth of the global burden of type 2 diabetes was attributable to PM_2·5 exposure, with an estimated 3·78 (95% uncertainty interval 2·68–4·83) deaths per 100 000 population and 167 (117–223) disability-adjusted life-years (DALYs) per 100 000 population. Approximately 13·4% (9·49–17·5) of deaths and 13·6% (9·73–17·9) of DALYs due to type 2 diabetes were contributed by ambient PM2·5, and 6·50% (4·22–9·53) of deaths and 5·92% (3·81–8·64) of DALYs by household air pollution. High burdens, in terms of numbers as well as rates, were estimated in Asia, sub-Saharan Africa, and South Am

关键词：

来源：评论

学校读者我要写书评

暂无评论

Driving in the Matrix: Can virtual worlds replace human-generated annotations for real world tasks?

Driving in the Matrix: Can virtual worlds replace human-gene...

引用

2017 IEEE International Conference on Robotics and Automation, ICRA 2017

作者： Johnson-Roberson, Matthew Barto, Charles Mehta, Rounak Sridhar, Sharath Nittur Rosaen, Karl Vasudevan, Ram Department of Naval Architecture and Marine Engineering University of Michigan Ann ArborMI48109 United States Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Robotics Program University of Michigan Ann ArborMI48109 United States Mechanical Engineering University of Michigan Ann ArborMI48109 United States

ISBN: (纸本)9781509046331

Deep learning has rapidly transformed the state of the art algorithms used to address a variety of problems in computer vision and robotics. These breakthroughs have relied upon massive amounts of human annotated training data. This time consuming process has begun impeding the progress of these deep learning efforts. This paper describes a method to incorporate photo-realistic computer images from a simulation engine to rapidly generate annotated data that can be used for the training of machine learning algorithms. We demonstrate that a state of the art architecture, which is trained only using these synthetic annotations, performs better than the identical architecture trained on human annotated real-world data, when tested on the KITTI data set for vehicle detection. By training machine learning algorithms on a rich virtual world, real objects in real scenes can be learned and classified using synthetic data. This approach offers the possibility of accelerating deep learning's application to sensor-based classification problems like those that appear in self-driving cars. The source code and data to train and validate the networks described in this paper are made available for researchers. © 2017 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：